-
```
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Your compiler (c++) is not compatible with the compiler Pytorch was
built with for this platform, which is …
-
Hello, I was trying to install this repository for 2 days, but I couldn't figure out how to do that and I tried all the PyTorch versions starting from 1.9.0 and up to 2.2.1. If anyone had a similar pr…
-
Traceback (most recent call last):
File "/content/video-retalking/inference.py", line 342, in
main()
File "/content/video-retalking/inference.py", line 33, in main
enhancer = FaceEnha…
-
(sadtalker) D:\ai\SadTalker>python inference.py --driven_audio D:\ai\temp\16.wav --source_image D:\ai\temp\msk.png --result_dir D:\ai\temp --still --preprocess full --enhancer gfpgan
./checkpoints\ep…
-
Testing 0 frame0
Error "slow_conv2d_cpu" not implemented for 'Half'
Tile 1/240
Traceback (most recent call last):
File "inference_realesrgan.py", line 166, in
main()
File "inference_re…
-
The Face Enhancer produces way too much resolution for it to look real.
Is there any way to down the resolution to find a middle ground?
Some videos have very blurry faces with no reason, the sou…
-
hi, i have a problem there.
when i run step4(normalization.py), find there is no directory "./data/target/train_yx2". what can i slove this error?
target_img = cv2.imread('./data/target/train_yx…
ml365 updated
5 years ago
-
Using FaceRestoreHelper needs `with threading.Semaphore()` to work within threads. I experienced this first in GFPGAN and later in our custom implementations.
This limits performance of GFPGAN a lo…
-
`main.py` for pipelline with scratch detection fails.
`python main.py --input_folder --checkpoint ./weights/Image_Enhancement/stage1_with_scratch/tf_keras.weights ./weights/Image_Enhancement/stag…
-
**3 Second audio/video processes in 2 mins 18 secs including enhance step (512x512):**
(1:43 face render, 45 seconds for Face Enhancer)
(Before the MPS mod, it took 20 minutes to process 3 second v…